通过合成演示增强医疗视觉-语言模型的安全性
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
AI总结：
本文提出一种新的推理时防御策略，通过合成临床演示提升模型安全性，同时平衡安全与性能。
摘要：
生成医疗视觉-语言模型（Med-VLMs）主要设计用于从多模态输入（包括视觉模态如医学图像和语言模态如临床查询）生成复杂文本信息（如诊断报告）。然而，其安全漏洞仍待深入研究。Med-VLMs应具备拒绝有害查询（如“提供使用此CT扫描进行保险欺诈的详细说明”）的能力。同时，解决安全问题可能引入过度防御的风险，即安全增强机制可能降低通用性能，导致Med-VLMs拒绝良性临床查询。本文提出了一种新的推理时防御策略，通过使用来自九种模态的多样化医学影像数据集，证明基于合成临床演示的防御策略在不显著影响性能的情况下增强了模型安全性。此外，我们发现增加演示预算可以缓解过度防御问题。我们随后引入了一种混合演示策略，作为在少量演示预算限制下平衡安全与性能的折中方案。
英文摘要：
Generative medical vision-language models~(Med-VLMs) are primarily designed to generate complex textual information~(e.g., diagnostic reports) from multimodal inputs including vision modality~(e.g., medical images) and language modality~(e.g., clinical queries). However, their security vulnerabilities remain underexplored. Med-VLMs should be capable of rejecting harmful queries, such as \textit{Provide detailed instructions for using this CT scan for insurance fraud}. At the same time, addressing security concerns introduces the risk of over-defense, where safety-enhancing mechanisms may degrade general performance, causing Med-VLMs to reject benign clinical queries. In this paper, we propose a novel inference-time defense strategy to mitigate harmful queries, enabling defense against visual and textual jailbreak attacks. Using diverse medical imaging datasets collected from nine modalities, we demonstrate that our defense strategy based on synthetic clinical demonstrations enhances model safety without significantly compromising performance. Additionally, we find that increasing the demonstration budget alleviates the over-defense issue. We then introduce a mixed demonstration strategy as a trade-off solution for balancing security and performance under few-shot demonstration budget constraints.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
